The Fault Mode Identification of Hydraulic Pump Based on MLSE and Support Vector Machine Optimized b

来源 :The 2nd International Conference on Structural Health Monito | 被引量 : 0次 | 上传用户:mkms2080
下载到本地 , 更方便阅读
声明 : 本文档内容版权归属内容提供方 , 如果您对本文有版权争议 , 可与客服联系进行内容授权或下架
论文部分内容阅读
  A new method which is multiscale local-maximum sample entropy(MLSE)is put forward to measure the complexity of time series in this paper.It can suppress the noise and interference of vibration signals and improve the precision of sample entropy on each time scale compared with multi-scale entropy.The MLSE of hydraulic pump under different status are treated as feature vectors.Artificial bee colony(ABC)algorithm is selected to optimize the structural parameters of support vector machine(SVM).The optimized SVM is applied to fault mode identification of hydraulic pump.The fault identification rate is higher compared with SVM and optimized SVM,and it is verified by the test data of hydraulic pump.
其他文献
The thin plate that uniaxial tensile stress loaded was used as the object in this paper.It adopt the critically refracted longitudinal(LCR)wave which based on the improved acoustic-elasticity theory a
At present,Yunnan power line cartier technology is about 73.7% in user acquisition local communication,and the average success rate of reading meter is about 75%.According to the principle of gross er
Identification of slight damage from measured dynamic responses incorporating significant noise is an ongoing challenge in the field of structural health monitoring,potentially requiting sophisticated
In order to solve problems of wired monitoring of structure impact damage such as large amount of wiring,high cost of installation or maintenance,and poor flexibility,a method of acquiring signal of s
Against the background of RPV irradiation embrittlement,this paper introduces the principle of Barkhausen noise detection and the design of detecting system of RPV irradiation embrittlement.Experiment
Fault diagnosis of rolling element beatings is of great importance to maintain the high reliability and long-term safe operation of rotating machinery.However,the weak fault feature is usually submerg
Structural health monitoring(SHM)is a crucial concern in engineering,which sets out to determine the health of a structure by reading information from an array of sensors that are embedded into the st
This paper presents a two dimensional(2D)linear PZTs array and spatial filter based damage and impact imaging method without using the Lamb wave group velocity.In this method,the damage signal is extr
Structural health monitoring has become more and more popular in application of damage diagnosis and safety assessment.Optical fiber sensors,as one of the most efficient sensing elements,for the super
A damage detection method for beam-type structures using ratio of natural frequency change and neural networks is proposed.With this method,ratio of natural frequency change is utilized as the damage